Model comparison
Inkling vs Step 3.5 Flash
Inkling is the stronger model overall, scoring 44.1 to 41.7 on the Noometry Index. Step 3.5 Flash costs 17× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Inkling scores higher in 6 categories and Step 3.5 Flash in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 21.2.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- Step 3.5 Flash accepts more context: 256K tokens versus 66K.
Side by side
| Inkling | Step 3.5 Flash | |
|---|---|---|
| Provider | Thinking Machines Lab | StepFun |
| Noometry Index | 44.1 | 41.7 |
| Released | 2026-07-15 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 66K | 256K |
| Max output | 66K | 256K |
| Input $ / M tokens | $1.87 | $0.10 |
| Output $ / M tokens | $4.68 | $0.30 |
| Results tracked | 41 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Inkling: 34.1 (#229), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1463 | 1436 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1412 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.5 (#76), Step 3.5 Flash: —
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1411 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.6 | — |
Math Step 3.5 Flash leads
Inkling: 31.2 (#198), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1482 | 1408 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.2 (#44), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1468 | 1422 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
Multilingual Inkling leads
Inkling: 54.2 (#49), Step 3.5 Flash: 50.7 (#115)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1434 | 1386 |
| LMArena Chinese | 1495 | 1448 |
| LMArena French | 1453 | 1421 |
| LMArena German | 1456 | 1404 |
| LMArena Japanese | 1428 | 1353 |
| LMArena Korean | 1401 | 1350 |
| LMArena Russian | 1430 | 1385 |
| LMArena Spanish | 1442 | 1419 |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Step 3.5 Flash: 73.3 (#119)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1427 | 1385 |
Long Context Inkling leads
Inkling: 43.9 (#79), Step 3.5 Flash: 42.8 (#112)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1436 | 1402 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Step 3.5 Flash: 59.0 (#108)
| Benchmark | Inkling | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1443 | 1403 |
| LMArena Creative Writing | 1390 | 1357 |
| LMArena Multi-Turn | 1436 | 1405 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Step 3.5 Flash?
Inkling is the stronger model overall, scoring 44.1 to 41.7 on the Noometry Index. Step 3.5 Flash costs 17× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 66K.
How many benchmarks do Inkling and Step 3.5 Flash share?
17 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Step 3.5 Flash has 19.